Seasonal and periodic autoregressive time series models used for forecasting analysis of rainfall data

Abstract

The amount of rainfall received over an area is an important factor in assessing availability of water to meet various demands for agriculture, industry, irrigation, generation of hydroelectricity and other human activities. In our study, we consider seasonal and periodic time series models for statistical analysis of rainfall data of Punjab, India. In this research paper we apply the Seasonal Autoregressive Integrated Moving Average and Periodic autoregressive model to analyse the rainfall data of Punjab. For evaluation of the model identification and periodic stationarity the statistical tool used are PeACF and PePACF. For model comparison we use Root mean square percentage error and forecast encompassing test. The results of this research will provide local authorities to develop strategic plans and appropriate use of available water resources.